Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1682 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 6.3602. Min Range: -6.3602

Max Act: 6.2500. Min Act: -0.0000

Data Index: 511631 (The Pile)

Max Activating Token Index: 509

Text #1

Max Range: 6.3602. Min Range: -6.3602

Max Act: 6.0087. Min Act: -0.0000

Data Index: 1123495 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 6.3602. Min Range: -6.3602

Max Act: 6.3602. Min Act: -0.0000

Data Index: 783232 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.9645. Min Act: -0.0000

Data Index: 1545089 (The Pile)

Max Activating Token Index: 402

Text #4

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.4423. Min Act: -0.0000

Data Index: 689712 (The Pile)

Max Activating Token Index: 699

Text #5

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.9343. Min Act: -0.0000

Data Index: 283085 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.9490. Min Act: -0.0000

Data Index: 762909 (The Pile)

Max Activating Token Index: 726

Text #7

Max Range: 6.3602. Min Range: -6.3602

Max Act: 6.1072. Min Act: -0.0000

Data Index: 676249 (The Pile)

Max Activating Token Index: 828

Text #8

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.6531. Min Act: -0.0000

Data Index: 47106 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.6120. Min Act: -0.0000

Data Index: 673794 (The Pile)

Max Activating Token Index: 392

Text #10

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.7458. Min Act: -0.0000

Data Index: 1931927 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.7514. Min Act: -0.0000

Data Index: 760076 (The Pile)

Max Activating Token Index: 470

Text #12

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.9358. Min Act: -0.0000

Data Index: 1878566 (The Pile)

Max Activating Token Index: 348

Text #13

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.3800. Min Act: -0.0000

Data Index: 334810 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.7242. Min Act: -0.0000

Data Index: 176206 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.8471. Min Act: -0.0000

Data Index: 106709 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.6290. Min Act: -0.0000

Data Index: 1748370 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.4433. Min Act: -0.0000

Data Index: 1895554 (The Pile)

Max Activating Token Index: 931

Text #18

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.7649. Min Act: -0.0000

Data Index: 1504776 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 6.3602. Min Range: -6.3602

Max Act: 5.4093. Min Act: -0.0000

Data Index: 423057 (The Pile)

Max Activating Token Index: 101